ML Anthology

Recovering Intrinsic Images from a Single Image

Marshall F. Tappen, William T. Freeman, Edward H. Adelson
NeurIPS 2002 pp. 1367-1374
/neurips/2002/tappen2002neurips-recovering/

Abstract

We present an algorithm that uses multiple cues to recover shading and reflectance intrinsic images from a single image. Using both color in- formation and a classifier trained to recognize gray-scale patterns, each image derivative is classified as being caused by shading or a change in the surface’s reflectance. Generalized Belief Propagation is then used to propagate information from areas where the correct classification is clear to areas where it is ambiguous. We also show results on real images.

PDF NeurIPS Semantic Scholar

Cite

Text

Tappen et al. "Recovering Intrinsic Images from a Single Image." Neural Information Processing Systems, 2002.

Markdown

[Tappen et al. "Recovering Intrinsic Images from a Single Image." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/tappen2002neurips-recovering/)

BibTeX

@inproceedings{tappen2002neurips-recovering,
  title     = {{Recovering Intrinsic Images from a Single Image}},
  author    = {Tappen, Marshall F. and Freeman, William T. and Adelson, Edward H.},
  booktitle = {Neural Information Processing Systems},
  year      = {2002},
  pages     = {1367-1374},
  url       = {https://mlanthology.org/neurips/2002/tappen2002neurips-recovering/}
}